@inproceedings{li-etal-2023-trends,
title = "Same Trends, Different Answers: Insights from a Replication Study of Human Plausibility Judgments on Narrative Continuations",
author = "Li, Yiru and
Lai, Huiyuan and
Toral, Antonio and
Nissim, Malvina",
editor = "Belz, Anya and
Popovi{\'c}, Maja and
Reiter, Ehud and
Thomson, Craig and
Sedoc, Jo{\~a}o",
booktitle = "Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.humeval-1.15",
pages = "190--203",
abstract = "We reproduced the human-based evaluation of the continuation of narratives task presented by Chakrabarty et al. (2022). This experiment is performed as part of the ReproNLP Shared Task on Reproducibility of Evaluations in NLP (Track C). Our main goal is to reproduce the original study under conditions as similar as possible. Specifically, we follow the original experimental design and perform human evaluations of the data from the original study, while describing the differences between the two studies. We then present the results of these two studies together with an analysis of similarities between them. Inter-annotator agreement (Krippendorff{'}s alpha) in the reproduction study is lower than in the original study, while the human evaluation results of both studies have the same trends, that is, our results support the findings in the original study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-trends">
<titleInfo>
<title>Same Trends, Different Answers: Insights from a Replication Study of Human Plausibility Judgments on Narrative Continuations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiru</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huiyuan</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We reproduced the human-based evaluation of the continuation of narratives task presented by Chakrabarty et al. (2022). This experiment is performed as part of the ReproNLP Shared Task on Reproducibility of Evaluations in NLP (Track C). Our main goal is to reproduce the original study under conditions as similar as possible. Specifically, we follow the original experimental design and perform human evaluations of the data from the original study, while describing the differences between the two studies. We then present the results of these two studies together with an analysis of similarities between them. Inter-annotator agreement (Krippendorff’s alpha) in the reproduction study is lower than in the original study, while the human evaluation results of both studies have the same trends, that is, our results support the findings in the original study.</abstract>
<identifier type="citekey">li-etal-2023-trends</identifier>
<location>
<url>https://aclanthology.org/2023.humeval-1.15</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>190</start>
<end>203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Same Trends, Different Answers: Insights from a Replication Study of Human Plausibility Judgments on Narrative Continuations
%A Li, Yiru
%A Lai, Huiyuan
%A Toral, Antonio
%A Nissim, Malvina
%Y Belz, Anya
%Y Popović, Maja
%Y Reiter, Ehud
%Y Thomson, Craig
%Y Sedoc, João
%S Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F li-etal-2023-trends
%X We reproduced the human-based evaluation of the continuation of narratives task presented by Chakrabarty et al. (2022). This experiment is performed as part of the ReproNLP Shared Task on Reproducibility of Evaluations in NLP (Track C). Our main goal is to reproduce the original study under conditions as similar as possible. Specifically, we follow the original experimental design and perform human evaluations of the data from the original study, while describing the differences between the two studies. We then present the results of these two studies together with an analysis of similarities between them. Inter-annotator agreement (Krippendorff’s alpha) in the reproduction study is lower than in the original study, while the human evaluation results of both studies have the same trends, that is, our results support the findings in the original study.
%U https://aclanthology.org/2023.humeval-1.15
%P 190-203
Markdown (Informal)
[Same Trends, Different Answers: Insights from a Replication Study of Human Plausibility Judgments on Narrative Continuations](https://aclanthology.org/2023.humeval-1.15) (Li et al., HumEval-WS 2023)
ACL